Geekbench ML Score

4766
ONNX CPU Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date August 27 2025 08:26 AM
Views 10

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model GMKtec NucBox_EVO-X2
Motherboard GMKtec GMKtec
Power PlanBalanced
CPU Information
Name AMD Ryzen AI Max+ 395
Topology 1 Processor, 16 Cores, 32 Threads
Identifier AuthenticAMD Family 26 Model 112 Stepping 0
Base Frequency 3.00 GHz
Cluster 116 Cores
L1 Instruction Cache32.0 KB x 16
L1 Data Cache48.0 KB x 16
L2 Cache1.00 MB x 16
L3 Cache32.0 MB x 2
Memory Information
Size 64.00 GB
Inference Information
Framework ONNX
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1742
325.9 IPS
 
Image Classification (F16)
100% 1734
324.4 IPS
 
Image Classification (I8)
99% 4643
868.8 IPS
 
Image Segmentation (F32)
100% 677
11.3 IPS
 
Image Segmentation (F16)
100% 655
10.9 IPS
 
Image Segmentation (I8)
98% 2906
48.5 IPS
 
Pose Estimation (F32)
100% 17323
21.0 IPS
 
Pose Estimation (F16)
100% 16964
20.5 IPS
 
Pose Estimation (I8)
100% 63557
77.0 IPS
 
Object Detection (F32)
100% 1846
137.8 IPS
 
Object Detection (F16)
100% 1820
135.9 IPS
 
Object Detection (I8)
62% 1993
148.8 IPS
 
Face Detection (F32)
100% 4576
54.4 IPS
 
Face Detection (F16)
100% 4429
52.7 IPS
 
Face Detection (I8)
89% 6287
74.7 IPS
 
Depth Estimation (F32)
100% 9873
76.6 IPS
 
Depth Estimation (F16)
100% 9916
76.9 IPS
 
Depth Estimation (I8)
96% 22760
176.5 IPS
 
Style Transfer (F32)
100% 30485
40.1 IPS
 
Style Transfer (F16)
100% 29472
38.8 IPS
 
Style Transfer (I8)
98% 49382
65.0 IPS
 
Image Super-Resolution (F32)
100% 4161
148.6 IPS
 
Image Super-Resolution (F16)
100% 3806
135.9 IPS
 
Image Super-Resolution (I8)
99% 5242
187.2 IPS
 
Text Classification (F32)
100% 1644
2.36 KIPS
 
Text Classification (F16)
100% 1545
2.22 KIPS
 
Text Classification (I8)
98% 1112
1.60 KIPS
 
Machine Translation (F32)
100% 2753
50.7 IPS
 
Machine Translation (F16)
100% 2636
48.5 IPS
 
Machine Translation (I8)
67% 4591
84.5 IPS
 

Compare

Set Baseline Geekbench 6 now available